© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4137
    Prev
    Next
    INDEX
    Explanations

    a seemingly random collection of word prefixes and suffixes

    oai_token-act-pair · gemini-2.0-flash

    proper nouns and place names

    np_token-act-pair-logits · gpt-4o-mini

    People, places, organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stood
    -0.51
    hiculo
    -0.48
    ocidad
    -0.46
    dasarkan
    -0.46
    uiente
    -0.45
    spě
    -0.45
     however
    -0.44
    InputModule
    -0.44
    guien
    -0.42
    чало
    -0.41
    POSITIVE LOGITS
    tonsoft
    1.04
    foundland
    0.99
    الحياه
    0.99
    StreetMap
    0.95
     disambiguazione
    0.94
    ьаж
    0.93
    withstanding
    0.93
    giveness
    0.90
    которые
    0.90
    oa̍t
    0.89
    Activations Density 1.710%

    No Known Activations